Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12860
    Prev
    Next
    INDEX
    Explanations

    C++ header file inclusions and their associated syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C++ include statements

    np_acts-logits-general · gemini-2.0-flash

    tablespoon measure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.71
    coroutines
    -0.55
     resultCode
    -0.53
    principalColumn
    -0.52
    WriteTagHelper
    -0.50
     tol
    -0.50
    vetica
    -0.49
    gdx
    -0.48
     []
    -0.47
     ['
    -0.47
    POSITIVE LOGITS
    includes
    0.77
    ..\
    0.72
    ../../
    0.68
    include
    0.68
    inc
    0.67
     neceffary
    0.67
     ../
    0.65
     itſelf
    0.65
    ftagPool
    0.64
    stdafx
    0.64
    Activations Density 0.170%

    No Known Activations